SWIRL

The change is one field in the SearchProvider

SWIRL builds the call from query_template, {url}?cx={cx}&key={key}&q={query_string}, and fills {url} from the SearchProvider's url field and {key} from credentials. Change those two and leave the rest of the provider as it is.

{
    "name": "Web - Google PSE",
    "active": true,
    "connector": "RequestsGet",
    "url": "https://api.specstream.ai/customsearch/v1",
    "query_template": "{url}?cx={cx}&key={key}&q={query_string}",
    "query_mappings": "cx=<keep your current value>,DATE_SORT=sort=date,PAGE=start=RESULT_INDEX,NOT_CHAR=-",
    "credentials": "key=<YOUR_SPECSTREAM_KEY>"
}

SpecStream accepts cx with any value and does not use it. start for paging is read; sort is accepted and not used. This is the call SWIRL then sends:

curl "https://api.specstream.ai/customsearch/v1?cx=any&key=$SPECSTREAM_API_KEY&q=open+source+vector+databases"

The same JSON, so SWIRL's mappings read it

SWIRL's Google provider maps FOUND to searchInformation.totalResults, RETRIEVED to queries.request[0].count and RESULTS to items, then each result's url to link, body to snippet and author to displayLink. SpecStream returns every one of those fields in Google's shape. It does not return pagemap or cacheId, so the payload fields SWIRL fills from them stay empty. The same call from Python:

import os, requests

reply = requests.get(
    "https://api.specstream.ai/customsearch/v1",
    params={"cx": "any", "key": os.environ["SPECSTREAM_API_KEY"], "q": "open source vector databases"},
).json()

print(reply["searchInformation"]["totalResults"], reply["queries"]["request"][0]["count"])
for item in reply["items"]:
    print(item["link"], item["snippet"], item["displayLink"])

$5 per 1,000 searches, with no daily limit

A search of up to 10 results costs $0.005, and SWIRL never asks for more than 10 in one call. There is no monthly plan and no daily limit. Credit you buy never expires, and a new account starts with $10 of credit, which covers 2,000 searches.

The most accurate web search API in the world

On SimpleQA Verified the SpecStream Search API scores 97.9 F-score on all 1,000 official questions, 978 of them correct. On WideSearch it scores 64.0 item F1 and 43.4 row F1 on all 200 official tasks. The Extract API scores 0.908 F1 on WCXB. Every score and its method is on the benchmarks page.

About one second a search, measured under load

The Google route runs on the fast search. On November 9, 2026 production took 1, 5, 10 and 20 fast searches a second and answered 718 of 720. The median was 0.82 s at 1 search a second and 1.07 s at 20 a second, and the 95th percentile stayed between 1.09 and 1.73 s. One account can send up to 8,800 searches a minute; a call over that is answered with Retry-After and is not charged.

You decide what is kept, on each key

Give SWIRL a key with zero_retention and a search made with it keeps no request text and no answer after the reply. The charge keeps the account, the key, the request ID, the price and the time. spend_cap_cents is the most the key can spend.

curl -X POST https://api.specstream.ai/v1/account/keys \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"name": "production", "scopes": ["account:read", "finds:spend"], "spend_cap_cents": 500000, "zero_retention": true}'

Search, pages and rows on one key

The same key reads up to 20 pages or documents a call with the Extract API at $0.80 per 1,000 pages, and a page with no text is not charged. Deep Search takes a request in plain words and returns every match on the live web as structured rows, at 5¢, 15¢ or $1 a row, with a source URL on every value. The most a run can cost is quoted before it starts.

Google Custom Search, until January 1, 2027

Existing customers can keep Google's default address until Google ends the API: $5 per 1,000 queries after 100 free a day, up to 10,000 a day. A new project gets no key. SpecStream costs the same $5 per 1,000, with no daily limit, behind the same SWIRL setting.

Vertex AI Search

Google's named alternative, for searching up to 50 domains, at $1.50 per 1,000 queries on Standard and $4.00 on Enterprise, called by POST at discoveryengine.googleapis.com with its own request. For full web search Google asks you to contact it. SpecStream searches the whole live web and answers the GET request SWIRL already sends.

Tavily

Search billed in credits at $0.008 each on pay as you go, with 1,000 free credits a month that reset on the first day of each month. SWIRL has no Tavily provider, so moving to it means new code and a new reply shape. SpecStream keeps your Google setup and charges $0.005 a search.